You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Document a recently solved problem to compound your team's knowledge
Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.
Use when implementing any feature or bugfix, before writing implementation code
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AISE 过程增强审查机制:端到端任务流程编排 + 机器签收(machine signoff)+ 6 种语言 pipe runner + 三阶段闭环 gate。
每个 runner 产出的 JUnit XML / stdout dump 被 sha256 + mtime + 生成窗口
记录到 .aise/runs/<run_id>/evidence.jsonl。下游 gate 不再信任 Agent 自报
"测试通过了",而是重读 evidence 校验:
evidence_tamperedevidence_window_violationExitPlanMode → aise_run_init.py (plan 校验 + run_id)
→ worker TDD → aise_scope_check.py (git diff vs scope)
→ aise_event.py (6 pipe) → aise_verify.py --verify-evidence
| Pipe | 适用 | 工具 | 端到端验收 | CI 平台 |
|---|---|---|---|:---:|---|
| go-test-json-to-junit | Go | go-junit-report | 6 ✅ | macOS + Linux |
| mvn-surefire | Java/Kotlin | mvn | 6 ✅ | Linux |
| pytest-junitxml | Python | pytest | 5 ✅ | macOS + Linux + Windows |
| jest-junit | JS/TS | fixture 内 jest | 4 ✅ | macOS + Linux |
| cargo-test-junit | Rust | cargo + cargo2junit | 3 ✅ | macOS + Linux |
| cargo-nextest-junit ⭐ | Rust | cargo-nextest(推荐)| 8 ✅ | macOS + Linux |
⭐ v3.5 新增,推荐 Rust 项目优先用 cargo-nextest-junit:原生 JUnit + stable Rust +
更快。详见 docs/rustc-bootstrap-risk.md。
gate 进程启动时一次性把 snapshot 读入内存,process-local 缓存。盘上 被中途篡改不影响本 gate 进程,关闭"中途偷换 plan"窗口。
declared kind=package + actual kind=testcase 且 parent_package 命中
→ 视为 cover。让 plan 用粗粒度 package 表达,runner 自动从 testcase 桥接。
defense_in_depth_check 路径分隔符归一(.\pkg\foo 自动匹配 ./pkg/**)_check_pid_alive Windows ctypes 调 kernel32.OpenProcess + STILL_ACTIVE(259)PYTHONUTF8=1 + 显式 encoding="utf-8")/aise-doctor
支持 --check-versions 对照兼容矩阵、--strict 严格模式、--export 导出报告。
lib/version_check.py — 工具版本对比引擎/plugin marketplace add https://github.com/heresun/AISE
/plugin install aise@aise
或本地开发:
git clone [email protected]:heresun/AISE ~/.claude/plugins/marketplaces/aise
/aise-doctor # 一键自检环境
/aise 给 data-bank 增加批量导出功能 # 启动 9 阶段端到端编排
详见 docs/tutorial.md + docs/aise-guide.md。
aise/
├── .claude-plugin/ marketplace.json + plugin.json
├── .github/workflows/ GitHub Actions CI 矩阵(18 jobs)
├── commands/ /aise + /aise-doctor slash command
├── skills/ 6 个内置 Skill(aise- 前缀)
├── scripts/
│ ├── aise_run_init.py v3.3 入口(plan 校验 + run_id)
│ ├── aise_event.py 6 pipe runner 调度
│ ├── aise_scope_check.py v3.3 scope gate
│ ├── aise_verify.py v1.1+ machine signoff
│ ├── aise_doctor.py v3.4 一键环境自检
│ ├── aise_snapshot.py plan.snapshot create/check/show
│ └── lib/
│ ├── lock.py 跨平台 mkdir 锁 + Windows ctypes pid
│ ├── event_runner.py PIPE_DEFS + preflight + defense + runtime_bin
│ ├── target_cover.py cross-kind targetCovers
│ ├── evidence.py sha256 + mtime 签收链
│ ├── snapshot.py plan.snapshot.json 防篡改
│ ├── preflight.py 通用工具预检 + 平台指引
│ ├── region_detect.py CN region 探测
│ ├── mirror_config.py 镜像源配置
│ ├── ansi.py ANSI 颜色过滤
│ ├── version_check.py 工具版本对比引擎
│ └── surefire_collector.py Maven XML hard-link + copy 回退
├── tests/ 247 测试(241 passed + 1 skip)
│ └── fixtures/ 5 语言示例项目(Go/Maven/Python/Jest/Rust)
├── templates/aise/ .aise/ 工作区模板
├── hooks/hooks.json PostToolUse + SessionStart 自动注册
├── docs/ 架构图 / 教程 / schema / 兼容性矩阵 / 完成度报告
├── LICENSE
└── README.md
npx claudepluginhub heresun/aise --plugin aiseAI 蜂群代码 Review - 自然语言交互, 智能默认, 反向确认, 偏好学习。跨厂商异构多模型协同 (Claude + DeepSeek + Qwen + GPT-5)。
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.